Fix CLIrrr2 model issue in app.py

app.py

@@ -2,173 +2,114 @@
 import os
 import uuid
 import io
-import base64
 from PIL import Image
 import gradio as gr
-import numpy as np
-
-# CLIP via Sentence-Transformers (text+image to same 512-dim space)
 from sentence_transformers import SentenceTransformer
-
-# Gemini (Google) client
 from google import genai
-
-# Qdrant client & helpers
 from qdrant_client import QdrantClient
 from qdrant_client.http.models import VectorParams, Distance, PointStruct
 
-# -------------------------
-#  CONFIG (reads env vars)
-# -------------------------
 GEMINI_API_KEY = os.environ.get("GEMINI_API_KEY")
 QDRANT_URL = os.environ.get("QDRANT_URL")
 QDRANT_API_KEY = os.environ.get("QDRANT_API_KEY")
 
-# -------------------------
-#  Initialize clients/models
-# -------------------------
-print("Loading CLIP model (this may take 20-60s the first time)...")
+print("Loading CLIP model...")
 MODEL_ID = "sentence-transformers/clip-ViT-B-32-multilingual-v1"
 clip_model = SentenceTransformer(MODEL_ID)
 
-# Gemini client
 genai_client = genai.Client(api_key=GEMINI_API_KEY) if GEMINI_API_KEY else None
 
-# Qdrant client
 if not QDRANT_URL:
-    raise RuntimeError("Please set QDRANT_URL environment variable")
+    raise RuntimeError("Set QDRANT_URL env var")
 qclient = QdrantClient(url=QDRANT_URL, api_key=QDRANT_API_KEY)
 
 COLLECTION = "lost_found_items"
 VECTOR_SIZE = 512
-
 if not qclient.collection_exists(COLLECTION):
     qclient.create_collection(
         collection_name=COLLECTION,
         vectors_config=VectorParams(size=VECTOR_SIZE, distance=Distance.COSINE),
     )
 
-# -------------------------
-#  Helpers
-# -------------------------
 def embed_text(text: str):
     return clip_model.encode(text, convert_to_numpy=True)
 
 def embed_image_pil(pil_img: Image.Image):
     return clip_model.encode(pil_img, convert_to_numpy=True)
 
-def gen_tags_from_image_file(file_obj) -> str:
-    """file_obj can be path or BytesIO"""
-    if genai_client is None:
+def gen_tags_from_image_file(img_bytes: io.BytesIO) -> str:
+    if not genai_client:
+        return ""
+    try:
+        file_obj = genai_client.files.upload(file=img_bytes)
+        prompt = ("Give 4 short tags (comma-separated) describing this item in the image. "
+                  "Respond only with tags.")
+        resp = genai_client.models.generate_content(model="gemini-2.5-flash",
+                                                   contents=[prompt, file_obj])
+        return resp.text.strip()
+    except Exception:
         return ""
-    uploaded_file = genai_client.files.upload(file=file_obj)
-    prompt_text = (
-        "Give 4 short tags (comma-separated) describing this item in the image. "
-        "Tags should be short single words or two-word phrases (e.g. 'black backpack', 'water bottle'). "
-        "Respond only with tags, no extra explanation."
-    )
-    response = genai_client.models.generate_content(
-        model="gemini-2.5-flash",
-        contents=[prompt_text, uploaded_file],
-    )
-    return response.text.strip()
 
-# -------------------------
-#  App logic: add item
-# -------------------------
 def add_item(mode: str, uploaded_image, text_description: str):
     item_id = str(uuid.uuid4())
     payload = {"mode": mode, "text": text_description}
 
-    if uploaded_image is not None:
-        # Save to BytesIO
-        img_bytes_io = io.BytesIO()
-        uploaded_image.save(img_bytes_io, format="PNG")
-        img_bytes_io.seek(0)
-
-        # Embed image
+    if uploaded_image:
+        img_bytes = io.BytesIO()
+        uploaded_image.save(img_bytes, format="PNG")
+        img_bytes.seek(0)
         vec = embed_image_pil(uploaded_image).tolist()
         payload["has_image"] = True
-
-        # Generate tags
-        try:
-            tags = gen_tags_from_image_file(img_bytes_io)
-        except Exception:
-            tags = ""
-        payload["tags"] = tags
-
-        # Store image as base64
-        img_bytes_io.seek(0)
-        payload["image_b64"] = base64.b64encode(img_bytes_io.read()).decode("utf-8")
+        payload["tags"] = gen_tags_from_image_file(img_bytes)
+        img_bytes.seek(0)
+        payload["image_b64"] = base64.b64encode(img_bytes.read()).decode("utf-8")
     else:
         vec = embed_text(text_description).tolist()
         payload["has_image"] = False
-
-        if genai_client:
-            try:
-                resp = genai_client.models.generate_content(
-                    model="gemini-2.5-flash",
-                    contents=f"Give 4 short, comma-separated tags for this item described as: {text_description}. Reply only with tags."
-                )
-                payload["tags"] = resp.text.strip()
-            except Exception:
-                payload["tags"] = ""
-        else:
-            payload["tags"] = ""
-
-    # Upsert into Qdrant
+        payload["tags"] = ""
+    
     point = PointStruct(id=item_id, vector=vec, payload=payload)
     qclient.upsert(collection_name=COLLECTION, points=[point], wait=True)
 
     return f"Saved item id: {item_id}\nTags: {payload.get('tags','')}"
 
-# -------------------------
-#  App logic: search
-# -------------------------
 def search_items(query_image, query_text, limit: int = 5):
-    if query_image is not None:
+    if query_image:
         qvec = embed_image_pil(query_image).tolist()
     elif query_text:
         qvec = embed_text(query_text).tolist()
     else:
-        return "Please provide a query image or text."
+        return "Provide query image or text."
 
     hits = qclient.search(collection_name=COLLECTION, query_vector=qvec, limit=limit)
-
     if not hits:
         return "No results."
 
     results = []
     for h in hits:
         payload = h.payload or {}
-        score = getattr(h, "score", None)
-        img_html = ""
-        if payload.get("has_image") and payload.get("image_b64"):
-            img_html = f'<img src="data:image/png;base64,{payload["image_b64"]}" width="200">'
+        score = getattr(h, "score", 0)
         results.append(
-            f"{img_html}<br>ID:{h.id}<br>Score:{float(score) if score else 0:.4f}<br>"
-            f"Mode:{payload.get('mode','')}<br>Tags:{payload.get('tags','')}<br>Text:{payload.get('text','')}"
+            f"ID:{h.id}\nScore:{float(score):.4f}\nMode:{payload.get('mode','')}\n"
+            f"Tags:{payload.get('tags','')}\nText:{payload.get('text','')}\n"
         )
 
-    return "<br><br>".join(results)
+    return "\n\n".join(results)
 
-# -------------------------
-#  Gradio UI
-# -------------------------
-with gr.Blocks(title="Lost & Found — Simple Helper") as demo:
-    gr.Markdown("## Lost & Found Helper — Upload items and search by image or text.")
+with gr.Blocks() as demo:
+    gr.Markdown("## Lost & Found Helper")
     with gr.Row():
         with gr.Column():
-            mode = gr.Radio(choices=["lost", "found"], value="lost", label="Add as")
+            mode = gr.Radio(["lost", "found"], value="lost", label="Add as")
             upload_img = gr.Image(type="pil", label="Item photo (optional)")
-            text_desc = gr.Textbox(lines=2, placeholder="Short description", label="Description (optional)")
+            text_desc = gr.Textbox(lines=2, placeholder="Short description", label="Description")
             add_btn = gr.Button("Add item")
-            add_out = gr.HTML(label="Add result")  # Changed to HTML to render images
+            add_out = gr.Textbox(interactive=False, label="Result")
         with gr.Column():
             query_img = gr.Image(type="pil", label="Search by image (optional)")
             query_text = gr.Textbox(lines=2, label="Search by text (optional)")
             search_btn = gr.Button("Search")
-            search_out = gr.HTML(label="Search results")  # HTML to render images
+            search_out = gr.Textbox(interactive=False, label="Search results")
 
     add_btn.click(add_item, inputs=[mode, upload_img, text_desc], outputs=[add_out])
     search_btn.click(search_items, inputs=[query_img, query_text], outputs=[search_out])